Natural Language Programming for Smart Home Scene Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional methods for programming smart home scenes require substantive coding and are not user-friendly, making it difficult for individuals to create custom programs using natural language inputs.

Innovation Solution

Implementing a system that allows users to program scenes using natural language, where compound verbal commands are parsed and mapped to control commands, enabling voice-based programming and execution of complex scenes with conditional and looping constructs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If traditional programming methods are used for smart home scenes, then programming precision and control capability are improved, but ease of operation and accessibility deteriorate

Engineering Contradiction:
Improveprogramming precisionVSAvoidease of operation
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The patent introduces a natural language processing intermediary layer between the user and the smart home control system. Users speak natural language commands which are processed through NLP to generate structured control commands, bridging the gap between simple user interaction and precise system control without requiring users to learn programming languages.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical interaction model (typing code, clicking buttons, navigating menus) with a voice-based natural language interface. This substitution allows users to program smart home scenes using conversational language instead of formal programming syntax, dramatically improving accessibility while maintaining control precision through automated command generation.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If natural language programming is implemented, then ease of operation and accessibility are improved, but device complexity and processing requirements worsen

Engineering Contradiction:
Improveease of operationVSAvoiddevice complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent segments the natural language processing task into distinct modular components: speech recognition module, natural language interpretation module, command generation module, and scene execution module. Each module handles a specific aspect of the processing chain, making the overall complex system manageable through functional decomposition and allowing independent optimization of each component.

Inventive Principle:
Principle #1Segmentation

3Ease of operation

If natural language processing is added, then ease of operation is improved, but loss of time in processing and system response worsens

Engineering Contradiction:
Improveease of operationVSAvoidprocessing time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent implements preliminary action by pre-processing and caching commonly used scene configurations, device groupings, and control patterns. When a user issues a natural language command, the system can quickly retrieve pre-defined templates and apply them, significantly reducing processing time compared to generating commands from scratch for every interaction.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11017772B1Natural language programming
Publication Date: 2021.05.25 JOSH AI INC
  • US11017772B1 patent drawing
  • US11017772B1 patent drawing
  • US11017772B1 patent drawing

AI summary

Audio content associated with a received verbal utterance is received. An operational meaning of the received verbal utterance comprising a compound input is recognized and determined at least in part by: determining that a first subset of the received verbal utterance is associated with a first recognized input; determining that a second subset of the received verbal utterance is associated with a second recognized input; and storing data that associates with a scene identifier a set of commands that includes a first command associated with the first recognized input and a second command associated with the second recognized input.